W
Wenxian Zheng
Researcher at Tsinghua University
Publications - 7
Citations - 543
Wenxian Zheng is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 2, co-authored 2 publications receiving 163 citations.
Papers
More filters
Journal ArticleDOI
Deep learning on image denoising: An overview.
TL;DR: A comparative study of deep techniques in image denoising by classifying the deep convolutional neural networks for additive white noisy images, the deep CNNs for real noisy images; the deepCNNs for blind Denoising and the deep network for hybrid noisy images.
Posted Content
Deep Learning on Image Denoising: An overview
TL;DR: In this paper, a comparative study of deep learning techniques for image denoising is presented, where the authors classify the deep convolutional neural networks (CNNs) for additive white noisy images, the deep CNNs for real noisy images; the deep ConvNets for hybrid noisy images.
Journal ArticleDOI
A Time-Efficient Protocol for Unknown Tag Identification in Large-Scale RFID Systems
TL;DR: An efficient unknown tag identification (EUTI) protocol that adopts a reservation mechanism to reduce collision slots and guide each unknown tag to skip empty slots when replying, thus saving execution time is proposed and a theoretical analysis of EUTI is provided to minimize execution time.
Journal ArticleDOI
Frontal-Centers Guided Face: Boosting Face Recognition by Learning Pose-Invariant Features
TL;DR: This work proposes a novel Frontal-Centers Guided Loss (FCGFace) to obtain highly discriminative features for face recognition, capable of adaptively adjusting the distribution of profile face features and narrowing the gap between them and frontal face features during different training stages to form compact identity clusters.
Journal ArticleDOI
Millimeter‐wave substrate integrated waveguide bandpass filters based on stepped‐impedance E‐shaped defected ground structures
TL;DR: In this article , a defected ground structure (DGS) is proposed for designing high-performance bandpass filters based on substrate integrated waveguide (SIW) platform, which consists of two complementary stepped-impedance E-shaped structures placed face-to-face.